Gray Level Co-occurrence Matrix Algorithm Research Articles

Echotexture Analysis of L4 Supraspinous Enthesis in Ankylosing Spondylitis.

Background:Enthesopathy is a main characteristic of ankylosing spondylitis (AS). However, ultrasonographic features of supraspinous enthesis in AS have not yet been reported.Methods:Forty-seven AS patients and 22 healthy individuals were enrolled and completed the study. L4 supraspinous entheses were assessed through an ultrasound (US) unit with the participants in a lateral decubitus position. Entheseal echogenicity was interpreted upon inspection of the US image. An entheseal grayscale (GS) value determination, along with an echotexture analysis using a gray-level co-occurrence matrix algorithm, was performed. The thoracolumbar fascia just above the enthesis was also analyzed. An enthesis-to-fascia ratio (EFR) of each texture feature was used for the purpose of intergroup comparison.Results:The prevalence of abnormal entheseal echogenicity in the AS and healthy groups was 19.1% and 13.6%, respectively (P = 0.42). The AS group experienced a higher GS EFR (0.56 [0.10–1.08] vs. 0.40 [0.12–0.89], P = 0.007), higher contrast EFR (0.62 [0.15–1.23] vs. 0.49 [0.23–1.33], P = 0.049), higher variance EFR (0.44 [0.06–1.21] vs. 0.35 [0.13–1.10], P = 0.023), and lower homogeneity EFR (1.07 [0.97–1.27] vs. 1.11 [1.04–1.19], P = 0.011) in comparison to the healthy group.Conclusion:Echotexture analysis identified the subtle structural changes in L4 supraspinous enthesis in AS patients. It proved to be superior to the inspection method and may possess the potential for providing early detection of supraspinous enthesopathy in AS.

Face Identification on Login Security Using Algorithm Combination of Viola-Jones and Cosine Similarity

Data security by using an alphanumeric combination password is no longer used, so it needs to be added security that is difficult to be manipulated by certain people. One type of security is the type of biometrics technology using face recognition which has different characteristics by combining the Viola-Jones algorithm to detect facial features, GLCM (Gray Level Co-occurrence Matrix) for extracting the texture characteristics of an image, and Cosine Similarity for the measurement of the proximity of the data (image matching). The image will be detected using the Viola-Jones algorithm to get face, eyes, nose, and mouth. The image detection results will be calculated the value of the texture characteristics with the GLCM (Gray Level Cooccurrence Matrix) algorithm. Image matching using cosine similarity will determine or match the data stored in the database with new image input until identification results are obtained. The results obtained in this study get the level of accuracy of the identification of the three algorithms by 77.20% with the amount of data that was correctly identified as many as 386 out of 500 images.Keywords: Security, face recognition, Viola-Jones, Cosine Similarity.

A computer aided diagnostic method for the evaluation of type II diabetes mellitus in facial thermograms.

Almost 50% of individuals around the globe are unaware of diabetes and its complications. So, an early screening of diabetes is very important at this current situation. To overcome the difficulties such as pain and discomfort to the subjects obtained from the biochemical diagnostic procedures; an infrared thermography is the diagnostic technique which measures the skin surface temperature noninvasively. Thus, the aim of our proposed study was to evaluate the type II diabetes in facial thermograms and to develop a computer aided diagnosis (CAD) system to classify the normal and diabetes. The facial thermograms (n = 160) including male (n = 79) and female (n = 81) were captured using FLIR A 305sc infrared thermal camera. The Haralick textural features were extracted from the facial thermograms based on gray level co-occurrence matrix algorithm. The TROI, TMAX, and TTOT are the statistical temperature parameters exhibited a significant negative correlation with HbA1c (r = - 0.421, - 0.411, - 0.242, p < 0.01 (TROI); r = - 0.259, p < 0.01(TMAX) and - 0.173, p < 0.05 (TTOT)). An optimal regression equation has been constructed by using the significant facial variables and standard HbA1c values. The model has achieved sensitivity, specificity, and accuracy rate as 91.42%, 88.57%, and 90% respectively. The anthropometrical variables, extracted textural features and temperature parameters were fed into the classifiers and their performances were compared. The Support Vector Machine outperformed the Linear Discriminant Analysis (84.37%) and k-Nearest Neighbor (81.25%) classifiers with the maximum accuracy rate of 89.37%. The developed CAD system has achieved 89.37% of accuracy rate for the classification of diabetes. Thus, the facial thermography could be used as the basic non-invasive prognostic tool for the evaluation of type II diabetes mellitus.

Klasifikasi Jenis Kacang-Kacangan Berdasarkan Tekstur Menggunakan Jaringan Syaraf Tiruan

Classification of types of beans is done on red beans, green beans, and peanuts. Texture features are obtained using the Gray Level Co-occurrence Matrix (GLCM) algorithm. The algorithm used to do the classification is Artificial Neural Networks (ANN). Experiments carried out with 3 different numbers of neurons in the hidden layer. Also, there are 17 types of training functions used. Each experiment scenario was repeated 5 times. Based on the experimental scenario, the best results are 99.8% for accuracy, 99.6% for precision and 99.8% for recall using 20 neurons in the hidden layer.

Selection of the optimum features to identify tooth decay in the panoramic images based on image texture analysis

&#x0D; &#x0D; &#x0D; &#x0D; The process of identifying pathological patterns in dental radiographic images (panorama images) is one of the most important stages of diagnosing diseases for dentists, and in light of the tremendous technological development, especially in the field of machine learning and pattern recognition, the Digital Image processing department has the most important role in the field of image fragmentation Extract the necessary features in order to identify pathological patterns and thus easily extract the pathological features of the input images. In this research, a methodology has been proposed to extract the features related to tooth decay from the digital Panorama radiographs obtained from the VaTech 400 device using image texture analysis based on the gray level co-occurrence matrix (GLCM) algorithm where the digital image was first entered into the computer and then converted to the Gray level, processed and noise removal facilities for the extraction process and then the statistical features of the GLCM matrix were extracted and then the choice of optimum features that lead to improved decay detection. The obtained results are shown increasing of accuracy of the results and improve the diagnosis process.&#x0D; &#x0D; &#x0D; &#x0D;

QR image feature extraction effectiveness based on metrics using spectral clustering and grey level Co-Occurrence matrix algorithm

Generation of key for data security is an important feature in cloud environment. Developing key from extracted feature is used to overcome the problem of mathematical attack and vulnerable. The proposed framework differs from prior work in that user-dependent Quick Response (QR) image are utilized to generate more compact and distinguishable features. This extensive paper aims to make analysis on GLCM (Grey level co-occurrence matrix) Algorithm features of QR image with spectral clustering algorithm features of QR image based on time factor. Which is used to the cloud user chooses the best mechanism based on their resource and requirements and help to make their extraction process effectively.

A non-contact approach for surface roughness prediction in CNC turning using a linear regression model

At present, the combination of non-contact type optical techniques and machine vision systems has a huge significance in the assessment of surface roughness. The non-contact measurement methods seem to have greater advantages over the conventional stylus method. Traditionally used contact-type surface roughness measurement technique assesses the roughness of machined component in a single line which is overcome by optical-based techniques and machine vision techniques with the capability to assess the whole machined surface. This paper deals with selected contact type stylus method and non-contact type machine vision methods for components prepared by turning of AISI 1040 steel at a variety of feed rates. The correlations have been developed between two dimensional (2D) surface roughness parameter and texture features for the components. The 2D surface roughness parameters have been recorded using a contact-type surface profilometer. On the other hand, the texture features have been extracted using a Gray level co-occurrence matrix algorithm (GLCM) and machine vision system. The correlation has been developed between extracted texture features of machined surfaces and measured 2D surface roughness parameters. The linear regression analysis has been performed in order to predict the surface roughness of machined components. The comparative results reveal a maximum measurement difference of 15% between contact types and presented a non-contact type assessment.

Human Tongue Thermography Could Be a Prognostic Tool for Prescreening the Type II Diabetes Mellitus.

Diabetes mellitus is one of the life threatening diseases over the globe, and an early prediction of diabetes is of utmost importance in this current scenario. International Diabetes Federation (IDF) reported nearly half of the world's population was undiagnosed and unaware of being developed into diabetes. In 2017, around 84 million individuals were living with diabetes, and it might increase to 156 million by the end of 2045 stated by IDF. Generally, the diagnosis of diabetes relies on the biochemical method that may cause uneasiness and probability of infections to the subjects. To overcome such difficulties, a noninvasive method is much needed around the globe for primary screening. A change in body temperature is an indication of various diseases. Infrared thermal imaging is relatively a novel technique for skin temperature measurement and turned out to be well known in the medical field due to being noninvasive, risk-free, and repeatable. According to traditional Chinese medicine, the human tongue is a sensitive mirror that reflects the body's pathophysiological condition. So, we have (i) analysed and classified diabetes based on thermal variations at human tongue, (ii) segmented the hot spot regions from tongue thermogram by RGB (red, green, blue) based color histogram image segmentation method and extracted the features using gray level co-occurrence matrix algorithm, (iii) classified normal and diabetes using various machine learning algorithms, and (iv) developed computer aided diagnostic system to classify diabetes mellitus. The baseline measurements and tongue thermograms were obtained from 140 subjects. The measured tongue surface temperature of the diabetic group was found to be greater than normal. The statistical correlation between the HbA1c and the thermal distribution in the tongue region was found to be r2 = 0.5688. The Convolutional Neural Network has outperformed the other classifiers with 94.28% accuracy rate. Thus, tongue thermograms could be used as a preliminary screening approach for diabetes prognosis.

Multi-population cooperative evolution-based image segmentation algorithm for complex helical surface image

Accurate image segmentation results would show a great significance to computer vision-based manufacturing for complex helical surface. However, the image segmentation for complex helical surface is always a difficult problem because of the uneven gray distribution and non-homogeneous feature patterns of its images. Therefore, a multi-direction evolutionary segmentation model is constructed and a multi-population cooperative evolution algorithm is proposed to solve the new model. According to the characteristics of gray distribution and feature patterns of complex helical surface image, an eigenvector extraction and description strategy is researched by combining gray level co-occurrence matrix algorithm with fractal algorithm, and the complex helical surface image can be described succinctly by gray feature and shape feature. Based on the description algorithm of image features, an image segmentation strategy using cooperative evolution from different eigenvector is discussed, and the helical surface image segmentation is decomposed from a single objective optimization problem to a multi-objective optimization problem to improve the accuracy of segmentation. Meanwhile, a multi-objective particle swarm optimization algorithm based on multi-directional evolution and shared archives is presented. Due to the fact that each eigenvector segmentation corresponds to one evolution direction, the collaboration of local and global segmentation can be realized by information sharing and interaction between evolution directions and the archive set. The comprehensive quality of non-dominated solution can be improved by the selection strategy of local and global optimal solution as well as the archive set maintenance. The practical numerical experiments for complex helical surface image segmentation are carried out to prove the validity of the proposed model and algorithm.

Cloud Classification Based on Images Texture Features

An identification of cloud imagery is part of the cloud observation process which is very important to know the potential for weather changes, especially in the Sultan Hasanuddin airport area. The purpose of this research is to build an artificial intelligence model to identify and classify texture patterns of cloud images. The research used 80 clouds images data contained in the Sultan Hasanuddin Airport area. The data consist of four types of clouds, Altocumulus, Cirrus, Cumulonimbus and Cumulus. In this research, a feature extraction process using Gray Level Co-occurrence Matrix (GLCM) algorithm and Support Vector Machine (SVM) is used for the classification process. We used a set of 4 GLCM features. The 4 selected features are contrast, correlation, energy and homogeneity. Training and testing data using cross validation method with three stages validation. The highest level of accuracy is found in the third stage validation with an accuracy value of 85%.

Static and Dynamic Algorithms for Terrain Classification in UAV Aerial Imagery

The ability to precisely classify different types of terrain is extremely important for Unmanned Aerial Vehicles (UAVs). There are multiple situations in which terrain classification is fundamental for achieving a UAV’s mission success, such as emergency landing, aerial mapping, decision making, and cooperation between UAVs in autonomous navigation. Previous research works describe different terrain classification approaches mainly using static features from RGB images taken onboard UAVs. In these works, the terrain is classified from each image taken as a whole, not divided into blocks; this approach has an obvious drawback when applied to images with multiple terrain types. This paper proposes a robust computer vision system to classify terrain types using three main algorithms, which extract features from UAV’s downwash effect: Static textures- Gray-Level Co-Occurrence Matrix (GLCM), Gray-Level Run Length Matrix (GLRLM) and Dynamic textures- Optical Flow method. This system has been fully implemented using the OpenCV library, and the GLCM algorithm has also been partially specified in a Hardware Description Language (VHDL) and implemented in a Field Programmable Gate Array (FPGA)-based platform. In addition to these feature extraction algorithms, a neural network was designed with the aim of classifying the terrain into one of four classes. Lastly, in order to store and access all the classified terrain information, a dynamic map, with this information was generated. The system was validated using videos acquired onboard a UAV with an RGB camera.

SAR village targets extraction and heterogonous image registration

Since the signal-to-noise ratio of synthetic aperture radar (SAR) image is low, it is difficult to match SAR images with optical images accurately. A new method of SAR village targets extraction and heterogonous image registration is proposed in this study. Median filter and partial differential method are first used to remove speckle noise; next, the grey level co-occurrence matrix algorithm is used by calculating four typical texture parameters of it to obtain preliminary regions of interest (ROI) of village targets and false alarm areas are cleared by proposed local-grey-level congruency method; then proper numbers of Fourier descriptors and morphological algorithms are used to describe ROI again to maintain the boundary features of targets better. Finally, HU moment invariants, which is combined with Euclidean distance and cosine similarity measurements, are utilised to achieve heterogonous image registration. The experimental results show that the root-mean-square-error of the registration image is small and the heterogonous registration image is accurate, demonstrating that the authors’ method is stable and accurate, and owns certain research value and broad application prospect as well.

Using Color and Texture Feature Extraction Technique to Retrieve Image

This paper proposes a content image retrieval using the texture and the color feature of the images. Although for extraction of texture feature, the “gray level co-occurrence matrix (GLCM) algorithm” is used and for extracting color feature the color histogram is used. The presented system is tested on the WANG database that contains a thousand color images with ten different classes by the help of three various type of distances

Abstract #4345 Psychosocial and environmental influences on prenatal maternal inflammation

This study explored the use of backscattered radiofrequency ultrasound signals combined with artificial neural network (ANN) technology to differentiate benign and malignant thyroid nodules, in comparison with conventional ultrasound techniques. The proposed method uses the gray level co-occurrence matrix algorithm and principal component analysis to identify principal characteristics for use as inputs in the ANN. The dataset consisted of 131 ultrasound images, of which 59 were benign and 72 were malignant, as determined by subsequent surgeries. The nodules were divided randomly into training, validation, and testing groups. Receiver operating characteristic curves (ROC) were drawn to compare the diagnostic efficiency of the ANN when applied to radiofrequency and conventional ultrasound images. The sensitivity, specificity, and accuracy of the ANN in predicting malignancy from the radiofrequency ultrasound images were 100, 91.5, and 96.2%, respectively; from conventional ultrasound, the corresponding values were 94.4, 93.2, and 93.9%, respectively. The area under the receiver operating characteristic curve (AUC) was also higher for radiofrequency than conventional ultrasound (AUC = 0.945 vs. 0.917, 95% confidence interval = 0.901–0.998 vs. 0.854–0.979, using a P-value of 0.26). We then classified each nodule into new risk categories according to the output of each sample generated by the proposed method. The malignancy risks in the proposed Categories 3, 4, and 5 were 0, 18.8, and 94.5%, respectively, compared with 0, 55.1, and 88.2% using the American College of Radiology’s Thyroid Imaging Reporting and Data System. Thus, this preliminary study initially indicated that the proposed method of using radiofrequency ultrasound and the ANN was more accurate at predicting malignancy and stratifying thyroid nodules than conventional ultrasound methods, thus offering significant potential to reduce the number of unnecessary thyroid biopsies.

Prediction of suspicious thyroid nodule using artificial neural network based on radiofrequency ultrasound and conventional ultrasound: A preliminary study

This study explored the use of backscattered radiofrequency ultrasound signals combined with artificial neural network (ANN) technology to differentiate benign and malignant thyroid nodules, in comparison with conventional ultrasound techniques. The proposed method uses the gray level co-occurrence matrix algorithm and principal component analysis to identify principal characteristics for use as inputs in the ANN. The dataset consisted of 131 ultrasound images, of which 59 were benign and 72 were malignant, as determined by subsequent surgeries. The nodules were divided randomly into training, validation, and testing groups. Receiver operating characteristic curves (ROC) were drawn to compare the diagnostic efficiency of the ANN when applied to radiofrequency and conventional ultrasound images. The sensitivity, specificity, and accuracy of the ANN in predicting malignancy from the radiofrequency ultrasound images were 100, 91.5, and 96.2%, respectively; from conventional ultrasound, the corresponding values were 94.4, 93.2, and 93.9%, respectively. The area under the receiver operating characteristic curve (AUC) was also higher for radiofrequency than conventional ultrasound (AUC = 0.945 vs. 0.917, 95% confidence interval = 0.901–0.998 vs. 0.854–0.979, using a P-value of 0.26). We then classified each nodule into new risk categories according to the output of each sample generated by the proposed method. The malignancy risks in the proposed Categories 3, 4, and 5 were 0, 18.8, and 94.5%, respectively, compared with 0, 55.1, and 88.2% using the American College of Radiology’s Thyroid Imaging Reporting and Data System. Thus, this preliminary study initially indicated that the proposed method of using radiofrequency ultrasound and the ANN was more accurate at predicting malignancy and stratifying thyroid nodules than conventional ultrasound methods, thus offering significant potential to reduce the number of unnecessary thyroid biopsies.

Application of Gray Level co-Occurrence Matrix Algorithm for Detection of Discrete Structural Changes in Cell Nuclei After Exposure to Iron Oxide Nanoparticles and 6-Hydroxydopamine.

The gray level co-occurrence matrix (GLCM) algorithm is a contemporary computational biology method which, today, is frequently used to detect small changes in texture that are not visible using conventional techniques. We demonstrate that the toxic compound 6-hydroxydopamine (6-OHDA) and iron oxide nanoparticles (IONPS) have opposite effects on GLCM features of cell nuclei. Saccharomyces cerevisiae yeast cells were treated with 6-OHDA and IONPs, and imaging with GLCM analysis was performed at three different time points: 30 min, 60 min, and 120 min after the treatment. A total of 200 cell nuclei were analyzed, and for each nucleus, 5 GLCM parameters were calculated: Angular second moment (ASM), Inverse difference moment (IDM), Contrast (CON), Correlation (COR) and Sum Variance (SVAR). Exposure to IONPs was associated with the increase of ASM and IDM while the values of SVAR and COR were reduced. Treatment with 6-OHDA was associated with the increase of SVAR and CON, while the values of nuclear ASM and IDM were reduced. This is the first study to indicate that IONPs and 6-OHDA have opposite effects on nuclear texture. Also, to the best of our knowledge, this is the first study to apply the GLCM algorithm in Saccharomyces cerevisiae yeast cells in this experimental setting.

Quantitative Ultrasound and B-Mode Image Texture Features Correlate with Collagen and Myelin Content in Human Ulnar Nerve Fascicles

We investigate the usefulness of quantitative ultrasound and B-mode texture features for characterization of ulnar nerve fascicles. Ultrasound data were acquired from cadaveric specimens using a nominal 30-MHz probe. Next, the nerves were extracted to prepare histology sections. Eighty-five fascicles were matched between the B-mode images and the histology sections. For each fascicle image, we selected an intra-fascicular region of interest. We used histology sections to determine features related to the concentration of collagen and myelin and ultrasound data to calculate the backscatter coefficient (–24.89 ± 8.31 dB), attenuation coefficient (0.92 ± 0.04 db/cm-MHz), Nakagami parameter (1.01 ± 0.18) and entropy (6.92 ± 0.83), as well as B-mode texture features obtained via the gray-level co-occurrence matrix algorithm. Significant Spearman rank correlations between the combined collagen and myelin concentrations were obtained for the backscatter coefficient (R = –0.68), entropy (R = –0.51) and several texture features. Our study indicates that quantitative ultrasound may potentially provide information on structural components of nerve fascicles.

An image-based method for the automatic recognition of cashmere and wool fibers

Due to the similarity of the morphological and textural structure between cashmere and wool fibers, it is a great challenge to identify these two animal fibers automatically. In this paper, one set of image-based method using the gray level co-occurrence matrix algorithm, the interactive measurement algorithm and the k-means clustering algorithm were proposed to identify cashmere and wool fibers quickly and accurately. Firstly, thousands of fiber images were observed by optical microscope and captured by digital camera and two different preprocessing methods were used to obtain the input images for the different feature extraction algorithm. Then the texture features were extracted by the gray level co-occurrence matrix and the diameter of fibers was measured by the interactive measurement algorithm. Finally, the extracted features were fed into the fiber identification system based on k-means algorithm for classification. The experimental results indicated that the proposed method was feasible for the recognition of cashmere and wool fibers with a high recognition of 94.29%.

Fruit Disease Detection Using GLCM And SVM Classifier

Analytics plays a critical role in detecting and analyzing the diseases. The proposed system identifies the fruits that are affected with diseases. It is done by collecting the raw data which is subjected to pre-processing. It results in a HSV (hue, saturation, value) converted image. After pre-processing, the resized format of the data is used to extract the information. In feature extraction the image is segmented and converted into matrix using Gray level co-occurrence matrix algorithm. The further classification is done and result is represented in the form of a decision tree using Support Vector Machine (SVM). The disease that affected the fruit is displayed along with the right fertilizer to be used for the plant.

Experimental analysis on relationship between roughness parameters and texture features of 6082T6 sandblasted components

Abstract In the present investigation, feasibility assessment has been deployed on 6082T6 alloy sand blasted components to correlate surface roughness parameters and surface attributes. A non-contact type high-speed machine vision system has been adopted to acquire the images of sandblasted work pieces. The surface profilometer has been used to quantify surface roughness parameters of different sandblasted work pieces. The measurement has been taken for various process conditions such as blasting pressure, the distance between work piece and nozzle, nozzle size and type of abrasive. The discrete wavelet transform has been adopted to enhance captured images in such a way that interfering noise can be eliminated. Gray level co-occurrence matrix (GLCM) algorithm has been used to extract texture features from pre-processed images of machined components. The result showed high correlation factors between texture feature contrast and surface roughness parameters, which confirms that proposed approach can be useful for roughness parameters prediction of high precision.